English Speech Emotion Classification Based on Multi-Objective Differential Evolution

Yue, Liya; Hu, Pei; Chu, Shu-Chuan; Pan, Jeng-Shyang

doi:10.3390/app132212262

Cited by 6 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is a need to evaluate 2 141 − 1 times which is nearly not possible to acquire an optimum feature from MFCCs and pitch features. Thus, the IEO is used as a feature selector to attain optimal solutions within the time range [26]. EO is used to randomly initialize the population position and its updated position can be described by: 𝑋 𝑖 (𝑛 + 1) = 𝑋 𝑒𝑞 (𝑛) + (𝑋 𝑖 (𝑛) − 𝑋 𝑒𝑞 (𝑛)) 𝐹(𝑛)…”

Section: B Ieo Based Fsmentioning

confidence: 99%

Empowering Cybersecurity Using Enhanced Rat Swarm Optimization With Deep Stack-Based Ensemble Learning Approach

Manickam,

Girija,

Kumar Dutta

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Cybersecurity is a vital technology and measures intended to protect networks, computers, information, and programs from threats and illegal access, modification, or damage. A security model covers a network and a computer safety method. Each system has antivirus software, firewalls, and an intrusion detection system (IDS). IDS helps in discovering and identifying illegal system behavior such as usage, copying, alteration, and damage. By estimating network traffic anomalies and patterns, deep learning (DL) models can enhance the detection abilities of IDS when compared to traditional rule-based methods. These models learn complex representations from data, authorizing them to recognize subtle and developing attack patterns. Techniques like recurrent neural network (RNN) and convolutional neural network (CNN) can be applied to progress consecutive or spatial features in network data, correspondingly. This manuscript empowers Cybersecurity by utilizing an Enhanced Rat Swarm Optimizer with a Deep Stack-Based Ensemble Learning (ERSO-DSEL) model. The ERSO-DSEL approach leverages feature selection (FS) with EL strategies to boost cybersecurity. In the ERSO-DSEL system, Z-score normalization is employed to measure the input data. Besides, an improved equilibrium optimizer (IEO) based FS approach is applied to choose a set of features. For cyberattack recognition, the ERSO-DSBEL approach uses the DSEL approach comprising three models namely deep neural network (DNN), long short-term memory (LSTM), and bidirectional LSTM (Bi-LSTM). Furthermore, the hyperparameter selection of these DL models takes place using the ERSO system. The solution result of the ERSO-DSBEL model is executed on a benchmark IDS database. A widecontrast study reported that the ERSO-DSBEL model accomplishes an enhanced accuracy outcome of 99.67% over other models of cybersecurity.

show abstract

Section: B Ieo Based Fsmentioning

confidence: 99%

Empowering Cybersecurity Using Enhanced Rat Swarm Optimization With Deep Stack-Based Ensemble Learning Approach

Manickam,

Girija,

Kumar Dutta

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The reason is that certain features have a significant impact, while others may be completely useless for emotion recognition. Feature selection methods simplify the task of selecting the most relevant features for classification algorithms [7,8]. These methods mainly eliminate the loss and overfitting problems caused by the curse of dimensionality, and improve the model's generalization.…”

Section: Introductionmentioning

confidence: 99%

Genetic Algorithm for High-Dimensional Emotion Recognition from Speech Signals

Yue,

Hu,

Chu

et al. 2023

Electronics

Self Cite

View full text Add to dashboard Cite

Feature selection plays a crucial role in establishing an effective speech emotion recognition system. To improve recognition accuracy, people always extract as many features as possible from speech signals. However, this may reduce efficiency. We propose a hybrid filter–wrapper feature selection based on a genetic algorithm specifically designed for high-dimensional (HGA) speech emotion recognition. The algorithm first utilizes Fisher Score and information gain to comprehensively rank acoustic features, and then these features are assigned probabilities for inclusion in subsequent operations according to their ranking. HGA improves population diversity and local search ability by modifying the initial population generation method of genetic algorithm (GA) and introducing adaptive crossover and a new mutation strategy. The proposed algorithm clearly reduces the number of selected features in four common English speech emotion datasets. It is confirmed by K-nearest neighbor and random forest classifiers that it is superior to state-of-the-art algorithms in accuracy, precision, recall, and F1-Score.

show abstract

Multimodal ML Strategies for Wind Turbine Condition Monitoring in Heterogeneous IoT Data Environments

Jameel,

Raazi,

Jameel

2024

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

English Speech Emotion Classification Based on Multi-Objective Differential Evolution

Cited by 6 publications

References 31 publications

Empowering Cybersecurity Using Enhanced Rat Swarm Optimization With Deep Stack-Based Ensemble Learning Approach

Empowering Cybersecurity Using Enhanced Rat Swarm Optimization With Deep Stack-Based Ensemble Learning Approach

Genetic Algorithm for High-Dimensional Emotion Recognition from Speech Signals

Multimodal ML Strategies for Wind Turbine Condition Monitoring in Heterogeneous IoT Data Environments

Contact Info

Product

Resources

About